Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to consistency or uniformity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    er
    -0.18
    essler
    -0.18
     latter
    -0.18
    scribe
    -0.16
    manship
    -0.15
    aso
    -0.15
    lest
    -0.15
    eger
    -0.15
    .parseFloat
    -0.15
    ม
    -0.15
    POSITIVE LOGITS
    ently
    0.35
    ively
    0.26
    encies
    0.21
    ency
    0.20
    ence
    0.18
    antly
    0.18
    cy
    0.17
    itution
    0.17
    aneously
    0.16
    å·±
    0.16
    Act Density 0.059%

    No Known Activations